Optimization & Theory

A Central Limit Theorem for Differentially Private Query Answering NeurIPS 2021 AC-GC: Lossy Activation Compression with Guaranteed Convergence NeurIPS 2021 Achieving On-Mobile Real-Time Super-Resolution With Neural Architecture and Pruning Search ICCV 2021 Achieving Robustness in Classification Using Optimal Transport With Hinge Regularization CVPR 2021 A Closer Look at Fourier Spectrum Discrepancies for CNN-Generated Images Detection CVPR 2021 ACMo: Angle-Calibrated Moment Methods for Stochastic Optimization AAAI 2021 A Compression-Compilation Co-Design Framework Towards Real-Time Object Detection on Mobile Devices AAAI 2021 A Convergence Analysis of Gradient Descent on Graph Neural Networks NeurIPS 2021 Activate or Not: Learning Customized Activation CVPR 2021 AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition ICCV 2021 Adaptive Consistency Prior Based Deep Network for Image Denoising CVPR 2021 Adaptive Curriculum Learning ICCV 2021 Adaptive Knowledge Driven Regularization for Deep Neural Networks AAAI 2021 Adaptive Proximal Gradient Methods for Structured Neural Networks NeurIPS 2021 Adaptive wavelet pooling for convolutional neural networks AISTATS 2021 Adder Attention for Vision Transformer NeurIPS 2021 AdderSR: Towards Energy Efficient Image Super-Resolution CVPR 2021 A Decomposition Model for Stereo Matching CVPR 2021 A Deeper Look at the Hessian Eigenspectrum of Deep Neural Networks and its Applications to Regularization AAAI 2021 A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima ICLR 2021 AdvantageNAS: Efficient Neural Architecture Search with Credit Assignment AAAI 2021 Adversarially Adaptive Normalization for Single Domain Generalization CVPR 2021 Adversarial Neuron Pruning Purifies Backdoored Deep Models NeurIPS 2021 Adversarial Robustness Guarantees for Random Deep Neural Networks ICML 2021 A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks AISTATS 2021